Related papers: The Implicit Curriculum: Learning Dynamics in RL w…
Reinforcement Learning with Verifiable Rewards (RLVR) is highly effective for enhancing LLM reasoning, yet recent evidence shows models like Qwen 2.5 achieve significant gains even with spurious or incorrect rewards. We investigate this…
Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates promising potential in advancing the reasoning capabilities of LLMs. However, its success remains largely confined to mathematical and code domains. This primary limitation…
Recent advances in reinforcement learning with verifiable rewards (RLVR) show that large language models enhance their reasoning abilities when trained with verifiable signals. However, due to reward sparsity, effectiveness depends heavily…
Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated promising gains in enhancing the reasoning capabilities of large language models. However, its dependence on domain-specific verifiers significantly restricts its…
We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative…
Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…
Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk…
Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' problems for training…
Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial…
Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision. We explore Reinforcement Learning from…
World models predict state transitions in response to actions and are increasingly developed across diverse modalities. However, standard training objectives such as maximum likelihood estimation (MLE) often misalign with task-specific…
Generating explanations for reinforcement learning (RL) is challenging as actions may produce long-term effects on the future. In this paper, we develop a novel framework for explainable RL by learning a causal world model without prior…
Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximization or variational…
Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual…
Curriculum reinforcement learning (CRL) improves the learning speed and stability of an agent by exposing it to a tailored series of tasks throughout learning. Despite empirical successes, an open question in CRL is how to automatically…
Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…
Although outcome-based reinforcement learning (RL) significantly advances the mathematical reasoning capabilities of Large Language Models (LLMs), its reliance on computationally expensive ground-truth annotations imposes a severe…
Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…
As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifiers. We study this phenomenon on inductive reasoning tasks,…
Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…